Survey on Different Techniques in SQL to Prepare Dataset for Data Mining

One of the basic tasks in data mining activity is data preprocessing and preparing dataset. Efficient data analysis can be made easier with datasets having columns in horizontal tabular layout. This paper presents an overview of data preprocessing and dataset preparation techniques using SQL. To prepare dataset if we use SQL aggregations they return one column per aggregated group. This is the limitation of SQL aggregation. In this paper we have proposed need of effective and optimized usage of SQL to build dataset using horizontal aggregations. Also if the result of horizontal aggregation i.e. horizontal layout is integrated with K-means clustering algorithm we can get proper clusters.